Merge pull request #10 from nealwp/error-dialog

Error dialog

Author: nealwp

.gitignore

@@ -13,4 +13,5 @@ lib/*
 *.json
 files
 *.drawio*
+*.docx
 .venv

pytest.ini

@@ -0,0 +1,2 @@
+[pytest]
+pythonpath = .

src/exporter/bell_summary.py

@@ -18,6 +18,7 @@ def generate_bell_format_summary(data):
     doc.add_paragraph(f'TYPE OF CLAIM:\t\t{data["claimant"].claim}')
     doc.add_paragraph(f'DATE OF APPLICATION:\t{datetime.strftime(data["claimant"].pdof, "%m/%d/%Y")}')
     doc.add_paragraph(f'ALLEGED ONSET DATE:\t{data["onset_date"]}')
+    doc.add_paragraph(f'DATE LATE INSURED:\t\t{data["claimant"].last_insured_date}')
     doc.add_paragraph(f'DOB:\t\t\t\t{data["birthdate"]}')
     doc.add_paragraph(f'AGE:\t\t\t\t{data["age"]}')
     doc.add_paragraph(f'EDUCATION:\t\t\t{data["education"]}')
@@ -66,6 +67,19 @@ def generate_bell_format_summary(data):
                 p = doc.add_paragraph()
                 p.add_run(f'{comment.date}: {comment.text} ({exhibit}/{comment.exhibit_page})')
 
+    doc.add_paragraph('')
+    doc.add_paragraph('')
+
+    doc.add_paragraph('CONSULTATIVE EXAM:')
+
+    doc.add_paragraph('')
+    doc.add_paragraph('')
+
+    doc.add_paragraph('MEDICAL-VOCATIONAL GRIDRULE AND/OR RULING:')
+
+    doc.add_paragraph('')
+    doc.add_paragraph('')
+
     for section in doc.sections:
         section.left_margin = Inches(1)
         section.right_margin = Inches(1)

src/pdf/__init__.py

@@ -27,6 +27,10 @@ def age(self) -> int:
             return None
 
     def age_at_onset(self) -> int:
+
+        if self.onset_date == "N/A":
+            return None
+
         if self.birthdate and self.onset_date:
             birthdate = datetime.strptime(self.birthdate, '%m/%d/%Y')
             onset_date = datetime.strptime(self.onset_date, '%m/%d/%Y')

src/pdf/scanner.py

@@ -129,14 +129,32 @@ def scan_pdf_for_summary(pdf_path):
 
 
 def parse_client_info(page_text):
-
-    lines = page_text.splitlines()
-    lines = [line for line in lines if line]
-    client_data = lines[:7]
     client_info = {}
-    for e in client_data:
-        e = e.split(':')
-        client_info[e[0]] = e[1].lstrip()
+    lines = page_text.splitlines()
+
+    for line in lines:
+        if line.startswith("Alleged Onset:"):
+            client_info["Alleged Onset"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("Application:"):
+            client_info["Application"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("Claim Type:"):
+            client_info["Claim Type"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("Claimant:"):
+            client_info["Claimant"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("Last Change:"):
+            client_info["Last Change"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("Last Insured:"):
+            client_info["Last Insured"] = line.split(":")[1].strip()
+            continue
+        if line.startswith("SSN:"):
+            client_info["SSN"] = line.split(":")[1].strip()
+            continue
+
     return client_info
 
 
@@ -152,41 +170,49 @@ def parse_work_history(page_text):
                     'job_title': e.split(": ")[1],
                     'intensity': '',
                     'skill_level': '',
-                    }
+                }
     return work_history
 
 
 def get_exhibits_from_pdf(doc):
-    try:
-        outlines = doc.get_outlines()
-        sys.setrecursionlimit(999999999)
-        index = 1
-        provider = ''
-        exhibits = {}
-        for (level, title, dest, a, se) in outlines:
-            if level == 2:
-                provider = title
-                id = provider.split(":")[0]
-                provider_name = provider.split(":")[1].replace("Doc. Dt.", "").replace("Tmt. Dt.", "").strip()
-                provider_dates = re.sub(r"\(\d* page.*", "", provider.split(":")[2]).strip()
-                from_date = provider_dates.split("-")[0]
-                try:
-                    to_date = provider_dates.split("-")[1]
-                except IndexError:
-                    to_date = from_date
-                ex = Exhibit(provider_name=provider_name, from_date=from_date, to_date=to_date, comments=[])
-                exhibits[id] = ex
-            if level == 3:
-                index += 1
-    except PDFNoOutlines:
-        exhibits = {}
-        sys.setrecursionlimit(1000)
-        print('PDF has no outlines to reference.')
-
+    exhibits = {}
+    outlines = doc.get_outlines()
+    sys.setrecursionlimit(999999999)
+    index = 1
+    for (level, title, dest, a, se) in outlines:
+        if level == 2:
+            id, provider_name, from_date, to_date = parse_title(title)
+            ex = Exhibit(provider_name=provider_name, from_date=from_date, to_date=to_date, comments=[])
+            exhibits[id] = ex
+        if level == 3:
+            index += 1
     sys.setrecursionlimit(1000)
     return exhibits
 
 
+def parse_title(title):
+    split_title = title.split(":")
+    id = split_title[0]
+    provider_name = split_title[1].replace("Doc. Dt.", "").replace("Tmt. Dt.", "").strip()
+
+    # if no dates, return empty
+    if len(split_title) == 2:
+        provider_name = re.sub(r"\(\d* page.*", "", provider_name).strip()
+        return (id, provider_name, "", "")
+
+    provider_dates = re.sub(r"\(\d* page.*", "", split_title[2]).strip().split("-")
+
+    # if one date, return both as date
+    if len(provider_dates) == 1:
+        date = provider_dates[0]
+        return (id, provider_name, date, date)
+
+    from_date = provider_dates[0]
+    to_date = provider_dates[1]
+
+    return (id, provider_name, from_date, to_date)
+
+
 def parse_page_comments(annots):
 
     page_comments = []

src/ui/errordialog.py

@@ -0,0 +1,14 @@
+from tkinter import Toplevel, Label, LEFT, Button
+
+
+class ErrorDialog(Toplevel):
+    def __init__(self, parent, error):
+        super().__init__(parent)
+        self.title("Error")
+        Label(self, text=error, anchor='w', justify=LEFT).pack(pady=5, padx=5)
+
+        Button(self, text='Close', command=self.destroy).pack(pady=10)
+
+        self.transient(parent)
+        self.grab_set()
+        self.geometry("+%d+%d" % (parent.winfo_rootx()+50, parent.winfo_rooty()+50))

src/ui/summaryform.py

@@ -1,10 +1,11 @@
 from datetime import datetime
-from tkinter import Toplevel, Button, Label, Entry, StringVar, Text, LabelFrame, Radiobutton
+from tkinter import Toplevel, Button, Label, Entry, StringVar, Text, LabelFrame, Radiobutton, LEFT
 from tkinter.ttk import Combobox
-
+from traceback import format_exc
 from src.helpers import get_save_path, get_file_path, get_age, get_age_at_onset
 from src.pdf.scanner import scan_for_comments, scan_pdf_for_summary
 from src.ui.workhistoryform import WorkHistoryForm
+from src.ui.errordialog import ErrorDialog
 from src.exporter import generate_summary
 
 
@@ -179,9 +180,15 @@ def _get_summary_data(self):
         modal.grab_set()
         modal.geometry("+%d+%d" % (self.winfo_rootx()+50, self.winfo_rooty()+50))
         self.update()
-        self.medical_record = scan_pdf_for_summary(self.pdf_path)
-        self._fill_entry_fields()
-        modal.destroy()
+        try:
+            self.medical_record = scan_pdf_for_summary(self.pdf_path)
+            self._fill_entry_fields()
+            modal.destroy()
+        except Exception:
+            modal.destroy()
+            error = format_exc()
+            error_modal = ErrorDialog(self, error)
+            self.update()
 
     def _fill_entry_fields(self):
         mr = self.medical_record

tests/helpers/example_page_1.txt

@@ -0,0 +1,27 @@
+Claimant: John Person Doe
+SSN: 000-00-0000
+Last Change: 01/01/1970
+Alleged Onset: N/A
+
+Claim Type: T16
+Application: 01/01/2023
+Last Insured: N/A
+
+A. Payment Documents/Decisions
+Title
+1A: Disability Determination Explanation - DDE
+2A: Disability Determination Transmittal - 831
+3A: T16 Cease/Continue Disability Determination and Transmittal - 832
+4A: Disability Determination Explanation - DDE
+5A: Disability Determination Explanation - DDE
+6A: T16 Cease/Continue Disability Determination and Transmittal - 832
+7A: Disability Determination Explanation - DDE
+
+Decision Date
+08/06/2018
+08/06/2018
+08/30/2022
+08/30/2022
+02/23/2023
+05/17/2023
+05/17/2023

tests/helpers/example_page_1_alt.txt

@@ -0,0 +1,41 @@
+Claimant: Jane Person Doe
+SSN: 000-00-0000
+Last Change: 01/01/1970
+Alleged Onset: 01/01/2009
+
+A. Payment Documents/Decisions
+Title
+1A: Disability Determination Transmittal - 831
+2A: Disability Determination Explanation - DDE
+3A: Disability Determination Transmittal - 831
+4A: Disability Determination Explanation - DDE
+
+Claim Type: T16
+Application: 02/26/2022
+Last Insured: N/A
+
+B. Jurisdictional Documents/Notices
+Title
+1B: T16 Notice of Disapproved Claim - L444
+2B: Request for Reconsideration - 561
+3B: T16 Disability Reconsideration Notice - L1130
+4B: SSA-1696 - Claimant’s Appointment of a Representative - 1696
+5B: Fee Agreement for Representation before SSA - FEEAGRMT
+6B: SSA-1696 - Claimant’s Appointment of a Representative - 1696
+7B: Fee Agreement for Representation before SSA - FEEAGRMT
+8B: Request for Hearing by ALJ - 501
+9B: Hearing Agreement Form - HRNGAGREEFRM
+10B: Outgoing ODAR Correspondence - OUTODARC
+11B: Outgoing ODAR Correspondence - OUTODARC
+12B: Request for Hearing Acknowledgement Letter - HRGACK
+13B: Hearing Agreement Form - HRNGAGREEFRM
+14B: Hearing Notice - 507
+15B: Acknowledge Notice of Hearing - 504
+
+D. Non-Disability Development
+Title
+1D: Application for Supplemental Security Income Benefits - 8000
+2D: Detailed Earnings Query - DEQY
+3D: Summary Earnings Query - SEQY
+4D: Certified Earnings Records - CERTERN
+5D: New Hire, Quarter Wage, Unemployment Query (NDNH) - NDNH

tests/test_pdfscanner.py

@@ -1,11 +1,71 @@
-from modules.pdfscanner import *
+from src.pdf.scanner import parse_title, parse_client_info
 
-file_path = r'.\\files\\2909274-cecilia_phillips-case_file_exhibited_bookmarked-8-10-2022- w notes.pdf'
 
-def test_read_medical_record():
-    medical_record = MedicalRecord(file_path)
-    assert(medical_record)
+def test_parse_title():
+    test_cases = [
+        {
+            "test": "6F: 6F - 1 of 13 Office Treatment Records - OFFCREC LIFESTREAM BEHAIVORAL CENTER Tmt. Dt.: 12/28/2016-08/30/2021 (23 pages)",
+            "expected": (
+                "6F",
+                "6F - 1 of 13 Office Treatment Records - OFFCREC LIFESTREAM BEHAIVORAL CENTER",
+                "12/28/2016",
+                "08/30/2021",
+            )
+        },
+        {
+            "test": "16F: 16F - 1 of 112 Emergency Department Records - EMERREC UF HEALTH GAINESVILLE Tmt. Dt.: 01/09/2023 (17 pages)",
+            "expected": (
+                "16F",
+                "16F - 1 of 112 Emergency Department Records - EMERREC UF HEALTH GAINESVILLE",
+                "01/09/2023",
+                "01/09/2023",
+            )
+        },
+        {
+            "test": "19F: 19F - 1 of 23 Medical Evidence of Record - MER VOCATIONAL REHABILITATION (12 pages)",
+            "expected": (
+                "19F",
+                "19F - 1 of 23 Medical Evidence of Record - MER VOCATIONAL REHABILITATION",
+                "",
+                "",
+            )
+        },
+    ]
 
-def test_get_exhibits_from_medical_record():
-    medical_record = MedicalRecord(file_path)
-    exhibits = medical_record.exhibits
+    for case in test_cases:
+        result = parse_title(case["test"])
+        assert result == case["expected"]
+
+
+def test_parse_client_info():
+    expected = [
+        {
+            "Alleged Onset": "N/A",
+            "Application": "01/01/2023",
+            "Claim Type": "T16",
+            "Claimant": "John Person Doe",
+            "Last Change": "01/01/1970",
+            "Last Insured": "N/A",
+            "SSN": "000-00-0000",
+        },
+        {
+            "Alleged Onset": "01/01/2009",
+            "Application": "02/26/2022",
+            "Claim Type": "T16",
+            "Claimant": "Jane Person Doe",
+            "Last Change": "01/01/1970",
+            "Last Insured": "N/A",
+            "SSN": "000-00-0000",
+        }
+    ]
+
+    inputs = [
+        "tests/helpers/example_page_1.txt",
+        "tests/helpers/example_page_1_alt.txt"
+    ]
+
+    for i, file in enumerate(inputs):
+        fd = open(file, "r")
+        page_one = str(fd.read())
+        result = parse_client_info(page_one)
+        assert result == expected[i]